Artificial intelligence and imaging technologies are transforming agriculture by improving accuracy, efficiency, and sustainability in crop management. Research conducted at the Machine Vision and Optical Sensor (MVOS) Lab at South Dakota State University integrates hyperspectral, fluorescence, and RGB imaging with machine learning and robotics to address major challenges in plant health monitoring, nutrient management, and automation. A hyperspectral imaging and AI-based framework for early detection of Sudden Death Syndrome (SDS) in soybean leaves used Genetic Algorithm-based band selection (504 to 908 nm) and ensemble classifiers, achieving over 98% accuracy, while a related SDS severity assessment using YOLOv11 reached a mean average precision of 0.97 and 82.7% classification accuracy. For corn, hyperspectral imaging and AI models estimated foliar nitrogen stress at three treatment levels (0, 50, and 100 kg N ha⁻¹) with accuracies ranging from 94% to 100% and mean absolute errors below 0.06. Fluorescence imaging combined with deep learning detected Escherichia coli contamination on citrus and spinach leaves with 88.4% and 92.0% accuracy, respectively, and an inference speed of 0.011 seconds per image. A YOLOv8-pose model for chili pepper orientation classification achieved 88.5% precision, improving robotic grasping during harvesting. Additionally, an AI-driven “see and spray” system demonstrated real time weed segmentation (mAP 0.879), a twofold latency reduction through TensorRT optimization, and accurate variable rate herbicide application validated by water-sensitive paper analysis. Collectively, these advancements demonstrate the potential of AI-driven imaging and robotics to create intelligent, sustainable, and scalable solutions for precision agriculture.
Speaker
 |
| |
| |
Pappu Yadav
Assistant Professor of Precision Agriculture AI Engineering
South Dakota State University (United States)
|
|
|
Pappu Kumar Yadav is an Assistant Professor in Agricultural and Biosystems Engineering at South Dakota State University, where he leads the Machine Vision and Optical Sensor Lab. He received his Ph.D. in Biological and Agricultural Engineering from Texas A&M University and his M.S. in Electrical Engineering from California State University, Fresno. He completed postdoctoral research at the University of Florida and also worked at the Center for Irrigation Technology at Fresno State. His research integrates artificial intelligence, computer vision, robotics, unmanned aircraft system, and remote sensing to advance precision agriculture, with applications in hyperspectral imaging, robotic harvesting, and variable-rate spraying. Dr. Yadav has published extensively in reputed journals and serves as a Review Editor for Frontiers in Plant Science and a Topic Editor for Frontiers in Artificial Intelligence. He has presented his work at leading forums, including SPIE Defense + Commercial Sensing, the International Conference on Precision Agriculture, and the American Society of Agricultural and Biological Engineers (ASABE) Annual International Meeting.
Event Details
FORMAT: Oral presentation followed by audience Q&A.
MENU: Coffee, decaf, tea and water will be available nearby.
SETUP: Theater seating.
